基于人工神经网络的误差模式保证校正

Q3 Engineering Telfor Journal Pub Date : 2022-01-01 DOI:10.5937/telfor2202051b

Srdan Brkic, P. Ivaniš, B. Vasic

{"title":"基于人工神经网络的误差模式保证校正","authors":"Srdan Brkic, P. Ivaniš, B. Vasic","doi":"10.5937/telfor2202051b","DOIUrl":null,"url":null,"abstract":"In this paper, we analyze applicability of single-and two-hidden-layer feed-forward artificial neural networks, SLFNs and TLFNs, respectively, in decoding linear block codes. Based on the provable capability of SLFNs and TLFNs to approximate discrete functions, we discuss sizes of the network capable to perform maximum likelihood decoding. Furthermore, we propose a decoding scheme, which use artificial neural networks (ANNs) to lower the error-floors of low-density parity-check (LDPC) codes. By learning a small number of error patterns, uncorrectable with typical decoders of LDPC codes, ANN can lower the error-floor by an order of magnitude, with only marginal average complexity incense.","PeriodicalId":37719,"journal":{"name":"Telfor Journal","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On guaranteed correction of error patterns with artificial neural networks\",\"authors\":\"Srdan Brkic, P. Ivaniš, B. Vasic\",\"doi\":\"10.5937/telfor2202051b\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we analyze applicability of single-and two-hidden-layer feed-forward artificial neural networks, SLFNs and TLFNs, respectively, in decoding linear block codes. Based on the provable capability of SLFNs and TLFNs to approximate discrete functions, we discuss sizes of the network capable to perform maximum likelihood decoding. Furthermore, we propose a decoding scheme, which use artificial neural networks (ANNs) to lower the error-floors of low-density parity-check (LDPC) codes. By learning a small number of error patterns, uncorrectable with typical decoders of LDPC codes, ANN can lower the error-floor by an order of magnitude, with only marginal average complexity incense.\",\"PeriodicalId\":37719,\"journal\":{\"name\":\"Telfor Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Telfor Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5937/telfor2202051b\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Telfor Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5937/telfor2202051b","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

摘要

本文分析了单隐层前馈人工神经网络(SLFNs)和双隐层前馈人工神经网络(TLFNs)在线性分组码译码中的适用性。基于slfn和tlfn可证明的逼近离散函数的能力，我们讨论了能够执行最大似然解码的网络的大小。此外，我们提出了一种利用人工神经网络(ann)来降低低密度奇偶校验(LDPC)码的错误层的译码方案。通过学习少量错误模式(LDPC码的典型解码器无法纠正)，人工神经网络可以将错误层降低一个数量级，而平均复杂度仅为边际。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

On guaranteed correction of error patterns with artificial neural networks

In this paper, we analyze applicability of single-and two-hidden-layer feed-forward artificial neural networks, SLFNs and TLFNs, respectively, in decoding linear block codes. Based on the provable capability of SLFNs and TLFNs to approximate discrete functions, we discuss sizes of the network capable to perform maximum likelihood decoding. Furthermore, we propose a decoding scheme, which use artificial neural networks (ANNs) to lower the error-floors of low-density parity-check (LDPC) codes. By learning a small number of error patterns, uncorrectable with typical decoders of LDPC codes, ANN can lower the error-floor by an order of magnitude, with only marginal average complexity incense.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Telfor Journal Engineering-Media Technology

CiteScore

1.50

自引率

0.00%

发文量

审稿时长

23 weeks

期刊介绍： The TELFOR Journal is an open access international scientific journal publishing improved and extended versions of the selected best papers initially reported at the annual TELFOR Conference (www.telfor.rs), papers invited by the Editorial Board, and papers submitted by authors themselves for publishing. All papers are subject to reviewing. The TELFOR Journal is published in the English language, with both electronic and printed versions. Being an IEEE co-supported publication, it will follow all the IEEE rules and procedures. The TELFOR Journal covers all the essential branches of modern telecommunications and information technology: Telecommunications Policy and Services, Telecommunications Networks, Radio Communications, Communications Systems, Signal Processing, Optical Communications, Applied Electromagnetics, Applied Electronics, Multimedia, Software Tools and Applications, as well as other fields related to ICT. This large spectrum of topics accounts for the rapid convergence through telecommunications of the underlying technologies towards the information and knowledge society. The Journal provides a medium for exchanging research results and technological achievements accomplished by the scientific community from academia and industry.